Paper Citation Record · LEDGER

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training

As of 7 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 2 inbound Pith citation observations for arXiv:2511.07328.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2511.07328 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T23:27:49.126341Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T10:15:53.843113Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-04T20:00:08.864260Z

Reference resolution

25 of 25 outbound references displayed

verified exact17
verified fuzzy5
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8bfb8344-32b3-4fcb-9a0e-6d424c84b6d6 · outbound

This paper cites AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-17T23:30:29.394019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d0fcb4eb-d514-4750-bb95-c791c51aa47a · outbound

This paper cites Titans: Learning to Memorize at Test Time.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Titans: Learning to Memorize at Test Time

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.406188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7d74f784-2f8c-47a7-99cd-18d493e89dfc · outbound

This paper cites ATLAS: Learning to Optimally Memorize the Context at Test Time.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training ATLAS: Learning to Optimally Memorize the Context at Test Time

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-17T23:30:29.428699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c7339f33-8617-4d22-9ec4-c3f1b4a5ae20 · outbound

This paper cites ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.411116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 38867d12-96cd-4dbc-9ad1-f49f9add0257 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T23:30:29.401973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4dc3d4ae-8d64-474f-a2d5-62b3ad5a8a11 · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.416978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 20654815-b85f-49d1-a8aa-3ccd243bf897 · outbound

This paper cites RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.389248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e5562e64-47ae-4174-bb25-22e3e6f2f154 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.422484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 95081a22-a75a-4dac-9d5e-189199a568e6 · outbound

This paper cites Graphreader: Building graph-based agent to enhance long- context abilities of large language models.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Graphreader: Building graph-based agent to enhance long- context abilities of large language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:30:30.879073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c6a6ce39-fbb8-4fa8-b5b1-dc08a9333863 · outbound

This paper cites Search-o1: Agentic Search-Enhanced Large Reasoning Models.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Search-o1: Agentic Search-Enhanced Large Reasoning Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.398249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e1ce6482-3250-4981-87bf-6452ff8eaf0a · outbound

This paper cites CoRR , volume =.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training CoRR , volume =

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T23:30:29.353465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ac8a2341-16b8-452a-86e8-a968563f74f2 · outbound

This paper cites V olodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Belle- mare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training V olodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Belle- mare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-17T23:30:29.375993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0a5e6281-f298-42b2-8051-3da9a6669148 · outbound

This paper cites AlphaEvolve: A coding agent for scientific and algorithmic discovery.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training AlphaEvolve: A coding agent for scientific and algorithmic discovery

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.362283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b844f2d0-1ec1-488b-be7b-8d641fb5c1c4 · outbound

This paper cites Associative Recurrent Memory Transformer.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Associative Recurrent Memory Transformer

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-17T23:30:29.357940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8d0759df-fa29-474e-8865-29015618e4ca · outbound

This paper cites Proximal Policy Optimization Algorithms.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Proximal Policy Optimization Algorithms

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.343945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e0b97536-1d38-4cec-920f-bd53d549d4e3 · outbound

This paper cites LongRoPE2: Near-Lossless LLM Context Window Scaling.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training LongRoPE2: Near-Lossless LLM Context Window Scaling

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-17T23:30:29.371511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1cf31d7d-5687-47f2-89e2-107ac7fc5f16 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:30:29.348567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1d45157d-4d54-464c-8da6-09f16e784f44 · outbound

This paper cites Replug: Retrieval-augmented black-box language models.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Replug: Retrieval-augmented black-box language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:30:30.885879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c2fe87de-981e-47a7-b369-713d88fcf688 · outbound

This paper cites Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T23:30:29.339160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9d33a6ae-d40d-46aa-98d5-df451438671d · outbound

This paper cites An Empirical Study of Mamba-based Language Models.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training An Empirical Study of Mamba-based Language Models

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:31:04.038637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9b2d34d0-89cf-4d71-8a2c-cf0fc03b0f5d · outbound

This paper cites Survey of Specialized Large Language Model.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Survey of Specialized Large Language Model

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-17T23:30:29.380641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d3e17ab4-198b-4693-b61a-321d2a371503 · outbound

This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training Hotpotqa: A dataset for diverse, explainable multi-hop question answering

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:30:30.892687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9d86fa28-113f-4ec1-beaf-dafe0293173c · outbound

This paper cites In Defense of RAG in the Era of Long-Context Language Models.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training In Defense of RAG in the Era of Long-Context Language Models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-17T23:30:29.385080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 73da3611-18de-4f85-8832-3a39fac089ae · outbound

This paper cites End-to-end beam retrieval for multi-hop question answering.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training End-to-end beam retrieval for multi-hop question answering

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:30:30.890110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f5072654-09a8-4bf4-9c71-809fb7d6a270 · outbound

This paper cites ThenF(x, y, t) =⟨w, R tv⟩.

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training ThenF(x, y, t) =⟨w, R tv⟩

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:30:30.882122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation a7ab0b17-d399-471c-ba8c-52e2adb59a4c · inbound

BitNet Text Embeddings cites this paper.

BitNet Text Embeddings Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-07-04T20:00:08.866092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e7cb965-7f61-4bce-bcbd-56a2bd992864 · inbound

BitNet Text Embeddings cites this paper.

BitNet Text Embeddings Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T10:15:53.843113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.